Omniscio

Gemini Provider

Google's Gemini CLI as an alternative session provider: how to enable it and add a key, which models you can pick, the readiness gaps and their click-to-fix, and the image, tool-marker and streaming behavior that differs from Claude.

On this page

What it is

Omniscio supports spawning Claude-Code-style sessions backed by Google's Gemini CLI as one of several alternative providers, alongside claude (the default), codex, and the other registry providers (Antigravity, DeepSeek, Kimi, GLM, MiniMax, Cursor, Hermes, Pi, Meta, Grok, OpenCode, OpenClaw).

What the user sees

A Gemini session looks identical in the sidebar and main pane to a Claude session — same status dots, same streaming bubbles, same Ctrl+Enter to send. The provider is invisible in normal chat. The only user-visible differences:

  • The session header shows the four-point Gemini bloom logo (Google's blue→purple→pink brand gradient), with no text label, instead of nothing. Every started session shows its engine mark next to the title — Claude included, in its brand orange (only logo-less internal engines like OpenClaw / orchestrator show nothing). The per-launch provider dropdown on a fresh session also shows the same bloom mark next to each row, in the same brand gradient.
  • Tool permission: Omniscio answers gemini-cli's ACP permission requests itself, through the SAME gate Claude's sessions run, so your Agent Permission Level decides — not a Gemini-specific mode. At Full trust a tool runs without prompting; at Autonomous an in-project edit or command runs and an outside-the-project write asks; at Guarded (a fresh install's default) an edit inside the project runs while a shell command or config edit is held on a card you answer; at Read-only almost everything asks. A dangerous-path tool (SSH keys, cloud credentials, shell rc files, /etc/passwd) is denied outright at every level, Full trust included, with a note in the session rather than a card. Before this, Gemini's seam could only allow or deny, so a level that would have asked produced a flat denial and a note — it now holds the request open exactly as a Claude session does.
  • It works in a copy of your project, not the real one. A Gemini session runs in its own git worktree (a separate copy of the repo on its own branch) by default, whatever your worktree-isolation setting says — the same barrier Grok and Antigravity get, and for the same reason: Gemini's tools run without Claude Code's own guardrail pass, so that copy is the structural thing standing between the session and your real checkout. You review and merge its work like any other session's. See session-isolation.md.

Where to find it

How to enable

Shown out of the box. Gemini and Codex are alternative providers, and the alternative-provider section is visible by default — Settings → Accounts → Show alternative AI providers ships ON (a profile that last saved before 3 Oct 2026 keeps the old Claude-only view until you turn it on). Switch that master OFF and the entire Gemini setup section below is hidden in Settings → Accounts; switch it back ON and the Gemini panel appears. With the master off, the per-project "Default provider" radio collapses to a single Claude row and the session header's provider switcher (ChangeProviderButton) is hidden — Gemini effectively does not exist in the UI even if every gate below is configured. Your saved API key, "Allow Gemini sessions" toggle, and per-project defaults are preserved across master-toggle flips.

You need these in place:

  1. Gemini CLI binary — must be present on PATH or installable from the same Settings panel.
  2. Settings → Account → Allow Gemini sessions toggle — off by default; a small opt-in step.
  3. Auth — sign in to Gemini, OR (optionally) paste a key. An API key is no longer required. If you've signed in to the Gemini CLI with Google (running gemini once and completing the browser sign-in), Omniscio spawns keyless and that login is used. You don't have to find a terminal yourself: once the Gemini CLI is installed, Settings → Accounts → Gemini shows a one-click Sign in with Google button that opens a real, visible terminal window and runs gemini in it (its first interactive run is the Google sign-in) — complete it there, then return (re-open Settings to confirm). Alternatively, paste a Gemini API key in Settings → Account → Gemini → API key (encrypted via safeStorage); a pasted key is OPTIONAL and, when present, is used instead of the login. Omniscio strips any stray GEMINI_API_KEY from your shell so it can't silently bill an account. With neither, a Gemini turn fails with a "sign in with gemini, or add a key" message. See cli-login-auth-contract.md.

Once the binary + toggle are green (and you're signed in or have a key), you can launch a Gemini session in three ways:

  • Per-launch override — on a fresh (zero-message) session, the ChangeProviderButton in the new session's main panel (the launch-config pickers on a fresh session) lets you pick a one-off provider before sending the first message. Non-ready providers appear aria-disabled with a "Set up…" / "Install…" suffix and deep-link to Settings.
  • Per-project default — Edit Project dialog (three-dot menu → Edit) has a "Default provider" section with three radios. Pick Gemini and the project's sidebar "+ New Session" button spawns Gemini automatically.
  • Programmatically — anything that creates a session with provider: 'gemini' (recipes, agent-driven sessions, the API). Same readiness gates apply on the backend.

How it behaves

Choosing the model

A fresh Gemini session lets you pick the model in the launch-config pickers (next to the provider chooser): Gemini 4 Neon (gemini-4-neon, Google's frontier coding and agent model with a 1M-token window — the priciest, paid Gemini API only, so a free-tier Google sign-in gets an error on the first turn), Gemini 4 Carbon (gemini-4-carbon, the deep-reasoning Gemini 4 model — paid API only), Gemini 4 Argon (gemini-4-argon, the efficient Gemini 4 model at the same per-token price as Carbon; also paid API only), Gemini 3.8 Flash (gemini-3.8-flash, newest GA Flash — the default), Gemini 3.7 Flash (gemini-3.7-flash) and Gemini 3.6 Flash (gemini-3.6-flash, earlier Flash generations), Gemini 3.5 Flash (gemini-3.5-flash, an older Flash whose output rate never took the promo cut), Gemini 3.5 Flash-Lite (gemini-3.5-flash-lite, cheapest — fast, lightweight tasks), Gemini 3.1 Pro (gemini-3.1-pro-preview, preview), or Gemini 2.5 Flash (gemini-2.5-flash, fast/affordable fallback). The pick is staged locally and applied when you send your first message (passed to the gemini CLI as --model); Use default omits the flag so Gemini picks its own. Gemini has no separate "reasoning effort" knob, and the list is Gemini's own — never your Claude default model. See start-a-new-session.md.

What it costs

Gemini sessions are metered. gemini-cli reports the turn's token usage over ACP, Omniscio prices those tokens at the picked model's published Google rate, and the session records both — so a Gemini session appears in your spend totals, the per-session cost chip and the engine breakdown alongside every other engine, marked "≈" because the figure is an estimate rather than a vendor bill. Rates come from ai.google.dev/gemini-api/docs/pricing: the 3.8 / 3.7 / 3.6 Flash generation is on an introductory $0.75 / $3.75 per million tokens (in / out) through 2026-12-31, rising to $1.50 / $7.50 from 2027-01-01. Gemini 4 Argon costs more: an introductory $2 / $10 per million tokens (in / out) and $0.10 per million cached input tokens through 2026-11-30, rising to $4 / $20 (cache $0.20) from 2026-12-01. Gemini 4 Neon costs the most: $3 / $15 per million tokens (in / out, thinking tokens included) and $0.15 per million cached input tokens. It is paid-tier only and supports implicit caching only. Measured live on 2026-11-20 through the ACP harness, each Neon turn also carries about 30,000 input tokens of gemini-cli's own setup (system prompt and skills list), roughly 9¢ before any real work. Gemini 4 Carbon is priced the same as Argon today: $2 / $10 per million tokens (in / out) and $0.10 per million cached input tokens through 2026-11-30, rising to $4 / $20 (cache $0.20) from 2026-12-01. Carbon is paid-tier only and supports implicit caching only — explicit context caching is not offered on it. Those December figures are not in the price table yet: the table holds the rate in force on the day it was last edited, so both Gemini 4 rows must be re-priced on 2026-12-01.

Two things to know if you are using a free Google account rather than a billed API key: the recorded figure is Google's list price for the work performed, not money leaving your account, and a turn your Gemini CLI cancelled or failed reports no usage at all — that is recorded as 0, which there is a true zero rather than "not reported". (Until 2026-09-25 Gemini recorded every turn as $0 because Omniscio read only the stop reason out of that same ACP response and discarded the usage; the history before that date under-reports Gemini spend.)

Per-project default

Each project remembers a default provider in the projectDefaultProviders setting (a Record<projectId, ProviderId>). Empty by default — every project falls back to Claude. Change it from the project's three-dot menu → Edit → Default provider radios; the change persists immediately.

When a project's default is set to Gemini but Gemini isn't ready (toggle off or binary missing), an Inbox card names the project and provider and says in plain words what is missing. Its button opens the Settings screen where the gap is fixed, and the card clears itself once the provider is usable. The project's sidebar row itself carries no readiness marker.

Error states and fixes

Two gap codes — same shape as the codex provider (the API key is optional, so it is NOT a readiness gate):

Gap What it means Click-to-fix lands you at…
toggle-off "Allow Gemini sessions" is OFF in Settings Settings → Account → Allow Gemini sessions toggle
binary-missing gemini CLI not on PATH Settings → Account → Gemini CLI binary panel

Auth (a Gemini Google sign-in or a pasted key) is checked at the turn, not as a readiness gate; with neither, the turn fails with a humanized "sign in with gemini, or add a key" message.

Detection survives a slow cold-start. binary-missing confirms the CLI via a --version probe (5 s budget); under heavy app load that probe can be killed before it answers, so detection falls back to the CLI's presence on disk at a known install dir (npm-global / well-known paths). An installed-but-slow Gemini CLI therefore never false-flags as missing, and a successful detection is cached so the check stops re-probing. See provider-registry-contract.md (a-cold-start-probe-does-not-report-a-present-binary-missing).

  • codex-provider.md — same launcher / readiness / per-project-default model, different binary + credential
  • openclaw-provider.md — separate "alternative provider" model (remote WebSocket gateway, not a local CLI)

Last verified 2026-11-12